corymbus_upsert_activity

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The warning 'Écrit dans le CRM de production' adds critical side-effect context beyond the annotations (which already indicate a non-read-only mutation). It also honestly notes that the creation schema is undocumented and advises verifying the result, adding transparency about reliability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence followed by a crucial warning. It front-loads the primary purpose (create/update) and packs the type mapping and production write warning without any wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the upsert semantics, type enum, production impact, and undocumented creation schema. While it doesn't describe return values (no output schema), the schema covers most parameters, and the tool's behavior is sufficiently clear for an upsert operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers 83% of parameters with descriptions. The description adds extra value by mapping type values (1=Tâche, 2=Appel entrant, etc.) and clarifying the id semantics (omit for create, provide for update), which enriches what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool creates (without id) or updates (with id) an activity, and enumerates activity subtypes (task, call, appointment, note, email). It distinguishes itself from sibling upsert tools for accounts, contacts, and opportunities by explicitly naming the resource type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage guidance on when to create vs. update based on presence of id, and warns that it writes to production. It does not explicitly mention alternatives or when not to use it, but the resource-specific wording makes the intended use obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.